Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms associated with dominance and power dynamics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    testdata
    -0.48
    Swiss
    -0.46
    Spr
    -0.46
     escar
    -0.44
     Freiw
    -0.43
    Medical
    -0.43
    rdata
    -0.43
    Spring
    -0.43
    Ther
    -0.42
     inton
    -0.42
    POSITIVE LOGITS
     dominance
    0.90
     domination
    0.83
     domínio
    0.82
     dominant
    0.71
     dominated
    0.71
     dominio
    0.70
    Domin
    0.70
     Domin
    0.69
    domin
    0.69
     Dominion
    0.69
    Act Density 0.749%

    No Known Activations